INDEX

Explanations

phrases that indicate comparisons or contrasts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 naked

-0.15

IVERY

-0.15

Î®ÏĤ

-0.14

Î±Î½Î¬

-0.14

utron

-0.14

 elig

-0.14

ÏĦÎ¹Î½

-0.13

Anc

-0.13

alties

-0.13

POSITIVE LOGITS

resse

0.16

 Raise

0.15

ilder

0.15

:init

0.14

unr

0.14

ÇĲ

0.14

aise

0.14

rame

0.14

ramework

0.14

iren

0.13

Activations Density 0.150%

phrases that indicate comparisons or contrasts

No Comments

No Known Activations